Detection of Railway Masts in Airborne LiDAR Data

Ariyachandra, Mahendrini Fernando; Brilakis, Ioannis

doi:10.1061/(asce)co.1943-7862.0001894

Cited by 28 publications

(26 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, the authors considered both masts and other pole-like object segmentation methods to derive the knowledge gaps. Readers can refer to the authors' previous work Ariyachandra and Brilakis, (2020a), for a comprehensive literature review of each of these methods.…”

Section: Mast Segmentationmentioning

confidence: 99%

“…The problem of segmenting railway elements in the form of labelled point clusters from PCDs has yet to be solved (Ariyachandra and Brilakis, 2019, 2020a, 2020b. Likewise, the 3D solid model generation of segmented railway element point clusters to represent their geometry is still in its inception.…”

Section: Gaps In Knowledge and Objectivesmentioning

confidence: 99%

“…The 2 nd refinement algorithm starts from the left side of the track and repeats over the spans between masts on the right side of the track. The details of the 2 nd refinement algorithm can be found in the authors' previous work, Ariyachandra and Brilakis, (2020a). This step gives the segmented point clusters of the masts, along with the position coordinates (…”

Section: Proposed Frameworkmentioning

confidence: 99%

See 2 more Smart Citations

Generating Railway Geometric Digital Twins from Airborne LiDAR Data

Ariyachandra¹,

Brilakis²

2021

Computing in Construction

Self Cite

View full text Add to dashboard Cite

The cost of the railway digital twinning process counteracts the expected benefits of the resulting model. State-of-the-art methods yielded promising results, yet they could not offer large-scale digital twinning required over kilometres without forfeiting precision and manual cost. The proposed framework exploits the potential of railway topology to perform better when detecting and modelling the geometry of railway elements in railway point clouds with varying geometric patterns. Experiments on 18 km railway datasets illustrate that the framework improves the current cost and benefit ratio by reducing the overall twinning time by 90% without using any prior information.

show abstract

Section: Mast Segmentationmentioning

confidence: 99%

Section: Gaps In Knowledge and Objectivesmentioning

confidence: 99%

Section: Proposed Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Generating Railway Geometric Digital Twins from Airborne LiDAR Data

Ariyachandra¹,

Brilakis²

2021

Computing in Construction

Self Cite

View full text Add to dashboard Cite

show abstract

“…We argue that the strengths of model-driven strategies (providing fast geometrical models without visual deformations [28]) are strong in the scenarios with very low point densities meaning the model-driven methods can create the gDTs of OLE elements despite poor densities and sparseness of the PCD. Hence, our method proposed a fitting of pre-defined parametric assemblies to the point segments obtained using previously sorted mast position coordinates [8]. This proposed method is a re-iterative method throughout the track; it exploits the railway geometric relations mentioned in section 4.1 and railway topology as key factors.…”

Section: Overviewmentioning

confidence: 99%

“…The automation of the twinning process will reduce the modelling time and ultimately save costs. We presented a method for generating railway masts as a first step to tackling this challenge [8], which also presented a method for removing the majority of the vegetation and other noise data from the input Point Cloud Data (PCD). The current paper addresses the next step; a method to automatically generate Geometric Digital Twin (gDT)s of railway Overhead Line Equipment (OLE) systems from airborne LiDAR data.…”

Section: Introductionmentioning

confidence: 99%

Digital Twinning of Railway Overhead Line Equipment from Airborne LiDAR Data

Ariyachandra¹,

Brilakis²

2020

Proceedings of the 37th International Symposium on Automation and Robotics in Construction (ISARC)

Self Cite

View full text Add to dashboard Cite

The automated generation of geometry-only digital twins of Overhead Line Equipment (OLE) system in existing railways from point clouds is an unsolved problem. Currently, this process is highly reliant upon manual inputs, needing 10 times more labour hours than scanning the physical asset. The resulting modelling cost counteracts the expected benefits of the digital twin. We tackle this challenge using a novel model-driven method that exploits the highly regulated and standardised nature of railways. It starts by restricting the search for OLE elements relative to point clusters of the railway masts. The resulting point clusters of the OLE elements are then converged with various parametric models of different catenary configurations to verify the presence of OLE elements and to find the best possible fit. The method outputs a geometry-only digital twin of the OLE system in Industry Foundation Classes (IFC) format. The method was tested on an 18 km railway point cloud and achieves overall detection rates of 93.2% F1 score for OLE cables and 98.1% F1 score for other OLE elements. The accuracy of the generated model is evaluated using distance-based metrics between the ground truth model and the automated model. The average modelling distance is 3.82 cm Root Mean Square Error (RMSE) for all 18 km data.

show abstract